diff repex_full_clustering.xml @ 2:09747b55badb draft

Uploaded

--- a/repex_full_clustering.xml	Mon Feb 03 02:33:59 2020 -0500
+++ b/repex_full_clustering.xml	Tue Apr 21 06:39:40 2020 -0400
@@ -1,4 +1,4 @@
-<tool id="repeatexplorer2" name="RepeatExplorer2 clustering: " version="2.3.7" >
+<tool id="repeatexplorer2" name="RepeatExplorer2 clustering: " version="2.3.8" >
     <stdio>
       <regex match="lastdb: can't open file: NEAR" source="stderr" level="fatal" description="Version of last is too old, use ver 956 or higher\n" />
       <regex match="Traceback" source="stderr" level="fatal" description="Unknown error" />
@@ -12,7 +12,7 @@
      <requirement type="package">imagemagick</requirement>
      <requirement type="package">mafft</requirement>
      <requirement type="package">blast</requirement>
-     <requirement type="package">diamond</requirement>
+     <requirement type="package" version="0.9.29" >diamond</requirement>
      <requirement type="package">blast-legacy</requirement>
      <requirement type="package">r-igraph</requirement>
      <requirement type="package">r-data.tree</requirement>
@@ -30,14 +30,14 @@
      <requirement type="package">r-rsqlite</requirement>
      <requirement type="package">r-rserve</requirement>
      <requirement type="package">bioconductor-biostrings</requirement>
-     <requirement type="package" version="2.3.7">repex_tarean</requirement>
+     <requirement type="package" version="2.3.8">repex_tarean</requirement>
      <requirement type="set_environment">REPEX</requirement>
      <requirement type="set_environment">REPEX_VERSION</requirement>
      <requirement type="package" version="0.9.1" >pyrserve</requirement>
    </requirements>
     <command >
       export PYTHONHASHSEED=0;
-      \${REPEX}/seqclust --sample ${sample} --output_dir=tarean_output --logfile=${log} --cleanup $paired --taxon $taxon
+      \${REPEX}/seqclust --sample ${read_sampling.sample} --output_dir=tarean_output --logfile=${log} --cleanup $paired --taxon $taxon
 
       #if $advanced_options.advanced:
       --mincl $advanced_options.size_threshold $advanced_options.keep_names $advanced_options.automatic_filtering  -D $advanced_options.blastx.options_blastx
@@ -82,7 +82,18 @@
 	       help="Input file must contain FASTA-formatted NGS reads. Illumina paired-end reads are recommended."/>
   <param name="paired" type="boolean" truevalue="--paired" falsevalue="" checked="True" label="Paired-end reads" help="If paired-end reads are used, left- and right-hand reads must be interlaced and all pairs must be complete. Example of the correct format is provided in the help below." />
  
-	<param name="sample" label="Sample size" type="integer" value="500000" min="10000"/>
+  <conditional name="read_sampling">
+    <param name="do_sampling" type="boolean" truevalue="true" falsevalue="false" checked="True" label="Use maximum processable sequence reads" />
+    <when value="true">
+      <!-- pass -->
+      <param name="sample" label="Sample size" hidden="True" type="integer" value="0" help="Number of sequence reads for clustering"/>
+    </when>
+    <when value="false">
+      <param name="sample" label="Sample size" type="integer" value="500000" min="10000" help="Number of reads for clustering"/>
+    </when>
+  </conditional>
+
+
   <param name="taxon" label="Select taxon and protein domain database version (REXdb)" type="select" help="Reference database of transposable element protein domains - REXdb - is used for annotation of repeats">
     <option value="VIRIDIPLANTAE3.0" selected="true">Viridiplantae version 3.0 </option>
     <option value="VIRIDIPLANTAE2.2" selected="true">Viridiplantae version 2.2</option>
@@ -117,11 +128,12 @@
 
       <conditional name="options">
         <param name="options" type="select" label="Similarity search options" help="Different similarity search parameters are used depending on the input data to adjust for differences in read length and error rate">
-          <option value="ILLUMINA" selected="true">Illumina reads, read length 100nt or more </option>
-          <option value="ILLUMINA_SHORT" selected="false">Illumina reads, shorter than 100nt (Do not use reads shorter than 50nt!) </option>
+          <option value="ILLUMINA" selected="true">Illumina reads, default, all-to-all search uses mgblast, minimal identity 90% </option>
           <option value="ILLUMINA_DUST_OFF" selected="false">Illumina reads, no masking of low complexity repeats  </option>
+          <option value="ILLUMINA_SENSITIVE_MGBLAST" selected="false">all-to-all search is performed using mgblast (W8, min PID 80) slow, experimental feature!</option>
+          <option value="ILLUMINA_SENSITIVE_BLASTPLUS" selected="false">all-to-all search is performed using blastn (W6, min PID 80) very slow, experimental feature!</option>
           <option value="OXFORD_NANOPORE" selected="false">
-            Pseudo short reads simulated from Oxford Nanopore data (experimental feature)
+            Pseudo short reads simulated from Oxford Nanopore data, experimental feature!
           </option>
         </param>
       </conditional>